Paper
InfoGatherer: Principled Information Seeking via Evidence Retrieval and Strategic Questioning
Authors
Maksym Taranukhin, Shuyue Stella Li, Evangelos Milios, Geoff Pleiss, Yulia Tsvetkov, Vered Shwartz
Abstract
LLMs are increasingly deployed in high-stakes domains such as medical triage and legal assistance, often as document-grounded QA systems in which a user provides a description, relevant sources are retrieved, and an LLM generates a prediction. In practice, initial user queries are often underspecified, and a single retrieval pass is insufficient for reliable decision-making, leading to incorrect and overly confident answers. While follow-up questioning can elicit missing information, existing methods typically depend on implicit, unstructured confidence signals from the LLM, making it difficult to determine what remains unknown, what information matters most, and when to stop asking questions. We propose InfoGatherer, a framework that gathers missing information from two complementary sources: retrieved domain documents and targeted follow-up questions to the user. InfoGatherer models uncertainty using Dempster-Shafer belief assignments over a structured evidential network, enabling principled fusion of incomplete and potentially contradictory evidence from both sources without prematurely collapsing to a definitive answer. Across legal and medical tasks, InfoGatherer outperforms strong baselines while requiring fewer turns. By grounding uncertainty in formal evidential theory rather than heuristic LLM signals, InfoGatherer moves towards trustworthy, interpretable decision support in domains where reliability is critical.
Metadata
Related papers
Gen-Searcher: Reinforcing Agentic Search for Image Generation
Kaituo Feng, Manyuan Zhang, Shuang Chen, Yunlong Lin, Kaixuan Fan, Yilei Jian... • 2026-03-30
On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers
Omer Dahary, Benaya Koren, Daniel Garibi, Daniel Cohen-Or • 2026-03-30
Graphilosophy: Graph-Based Digital Humanities Computing with The Four Books
Minh-Thu Do, Quynh-Chau Le-Tran, Duc-Duy Nguyen-Mai, Thien-Trang Nguyen, Khan... • 2026-03-30
ParaSpeechCLAP: A Dual-Encoder Speech-Text Model for Rich Stylistic Language-Audio Pretraining
Anuj Diwan, Eunsol Choi, David Harwath • 2026-03-30
RAD-AI: Rethinking Architecture Documentation for AI-Augmented Ecosystems
Oliver Aleksander Larsen, Mahyar T. Moghaddam • 2026-03-30
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.05909v1</id>\n <title>InfoGatherer: Principled Information Seeking via Evidence Retrieval and Strategic Questioning</title>\n <updated>2026-03-06T04:55:03Z</updated>\n <link href='https://arxiv.org/abs/2603.05909v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.05909v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>LLMs are increasingly deployed in high-stakes domains such as medical triage and legal assistance, often as document-grounded QA systems in which a user provides a description, relevant sources are retrieved, and an LLM generates a prediction. In practice, initial user queries are often underspecified, and a single retrieval pass is insufficient for reliable decision-making, leading to incorrect and overly confident answers. While follow-up questioning can elicit missing information, existing methods typically depend on implicit, unstructured confidence signals from the LLM, making it difficult to determine what remains unknown, what information matters most, and when to stop asking questions. We propose InfoGatherer, a framework that gathers missing information from two complementary sources: retrieved domain documents and targeted follow-up questions to the user. InfoGatherer models uncertainty using Dempster-Shafer belief assignments over a structured evidential network, enabling principled fusion of incomplete and potentially contradictory evidence from both sources without prematurely collapsing to a definitive answer. Across legal and medical tasks, InfoGatherer outperforms strong baselines while requiring fewer turns. By grounding uncertainty in formal evidential theory rather than heuristic LLM signals, InfoGatherer moves towards trustworthy, interpretable decision support in domains where reliability is critical.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n <published>2026-03-06T04:55:03Z</published>\n <arxiv:comment>Under review</arxiv:comment>\n <arxiv:primary_category term='cs.CL'/>\n <author>\n <name>Maksym Taranukhin</name>\n </author>\n <author>\n <name>Shuyue Stella Li</name>\n </author>\n <author>\n <name>Evangelos Milios</name>\n </author>\n <author>\n <name>Geoff Pleiss</name>\n </author>\n <author>\n <name>Yulia Tsvetkov</name>\n </author>\n <author>\n <name>Vered Shwartz</name>\n </author>\n </entry>"
}